---
base_model: openai/whisper-large-v3
datasets:
- google/fleurs
library_name: transformers
license: apache-2.0
metrics:
- wer
model-index:
- name: whisper-large-v3-English-Version2
  results: []
language:
- en
pipeline_tag: automatic-speech-recognition
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# whisper-large-v3-English-Version2

This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the fleurs dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1802
- Wer: 5.4448

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 3e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- training_steps: 6000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer    |
|:-------------:|:-------:|:----:|:---------------:|:------:|
| 0.1778        | 5.3333  | 2000 | 0.1887          | 5.6330 |
| 0.1529        | 10.6667 | 4000 | 0.1814          | 5.4587 |
| 0.1408        | 16.0    | 6000 | 0.1802          | 5.4448 |


### Framework versions

- PEFT 0.12.1.dev0
- Transformers 4.45.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1